© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43019
    Prev
    Next
    INDEX
    Explanations

    private sector or practice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ´å¥Ĺ
    -0.07
    olen
    -0.06
    æĸ°åıijå±ķçIJĨ念
    -0.06
    æĴŃç§į
    -0.06
    acro
    -0.06
    ixon
    -0.06
    æĬ½è±¡
    -0.06
    è¸ıè¸ıå®ŀå®ŀ
    -0.06
    交代
    -0.06
    ei
    -0.06
    POSITIVE LOGITS
     privately
    0.15
    æ°ijéĹ´
    0.15
     private
    0.14
    ç§ģ人
    0.14
    æ°ijéĸĵ
    0.13
    ç§ģèĩª
    0.13
     prywat
    0.13
    èĩªåıij
    0.13
    /private
    0.13
    ç§ģèIJ¥
    0.12
    Activations Density 0.300%

    No Known Activations